1. M.I. Jaime Alfonso Reyes ´Cortés

2.  The basic task for any probabilistic inference system is to compute the posterior probability distribution for a set of query nodes, given values for some evidence nodes.  This task is called belief updating or probabilistic inference.

3.  Two node network  A two node network  If there is evidence about the parent node, say X = x, then the posterior probability (or belief) for Y can be read straight from the value in CPT  If there is evidence about the child node, say Y = y, then the inference task of updating the belief for X is done using

4.  P(x) is the prior and (x) = P(Y = y| X= x) is the likelihood  Note that we don’t need to know the prior for the evidence. Since the beliefs for all the values of X must sum to one (due to the Total Probability), we can compute  as a normalizing constant

5.  Three node chain  If we have evidence about the root node, X=x, updating in the same direction as the arcs involves the simple application of the chain rule, using the independencies implied in the network

6.  If we have evidence about the leaf node, Z=z, the diagnostic inference to obtain Bel(X) is done with the application of Bayes’ Theorem and the chain rule

7.  Exact inference in polytrees  polytree (or “forest”)  Polytrees have at most one path between any pair of nodes; hence they are also referred to as singly- connected networks  Assume X is the query node, and there is some set of evidence nodes E (not including X)  The task is to update Bel(X) by computing P(X|E)  The local belief updating for X must incorporate evidence from all other parts of the network

9.  evidence can be divided into:

18.  Kevin B. Korb, Ann E. Nicholson. Bayesian Artificial Intelligence, CHAPMAN & HALL/CRC. England, 2004.